summaryrefslogtreecommitdiffstats
path: root/options/options.h
diff options
context:
space:
mode:
authorPhilip Langdale <philipl@overt.org>2017-05-29 09:48:10 -0700
committerwm4 <wm4@nowhere>2017-06-03 16:41:03 +0200
commit7424651b9637082f71deab9fcc87111e2d9df13f (patch)
treee5d4813a3195e56d39bd313900a765bc69d9e40d /options/options.h
parent7e889e5e637536cba3dfced3962ab87d7c8ea01f (diff)
downloadmpv-7424651b9637082f71deab9fcc87111e2d9df13f.tar.bz2
mpv-7424651b9637082f71deab9fcc87111e2d9df13f.tar.xz
vo_opengl: hwdec_cuda: Support separate decode and display devices
In a multi GPU scenario, it may be desirable to use different GPUs for decode and display responsibilities. For example, if a secondary GPU has better video decoding capabilities. In such a scenario, we need to initialise a separate context for each GPU, and use the display context in hwdec_cuda, while passing the decode context to avcodec. Once that's done, the actually hand-off between the two GPUs is transparent to us (It happens during the cuMemcpy2D operation which copies the decoded frame from a cuda buffer to the OpenGL texture). In the end, the bulk of the work is around introducing a new configuration option to specify the decode device.
Diffstat (limited to 'options/options.h')
-rw-r--r--options/options.h2
1 files changed, 2 insertions, 0 deletions
diff --git a/options/options.h b/options/options.h
index bfe7d42bcf..851b9c507f 100644
--- a/options/options.h
+++ b/options/options.h
@@ -336,6 +336,8 @@ typedef struct MPOpts {
struct angle_opts *angle_opts;
struct cocoa_opts *cocoa_opts;
struct dvd_opts *dvd_opts;
+
+ int cuda_device;
} MPOpts;
struct dvd_opts {